{"total":151,"rows":[{"id":"2205.10330","title":"A Review of Safe Reinforcement Learning: Methods, Theory and Applications","created":"2022-05-20","cited_by_count":181,"area":null},{"id":"2310.04373","title":"Confronting Reward Model Overoptimization with Constrained RLHF","created":"2023-10-06","cited_by_count":96,"area":"alignment"},{"id":"2205.11814","title":"Penalized Proximal Policy Optimization for Safe Reinforcement Learning","created":"2022-05-24","cited_by_count":68,"area":null},{"id":"2209.07089","title":"Constrained Update Projection Approach to Safe Policy Optimization","created":"2022-09-15","cited_by_count":58,"area":null},{"id":"2103.05134","title":"Constrained Learning with Non-Convex Losses","created":"2021-03-08","cited_by_count":42,"area":null},{"id":"2102.11941","title":"State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards","created":"2021-02-23","cited_by_count":40,"area":null},{"id":"2110.15767","title":"Adversarial Robustness with Semi-Infinite Constrained Learning","created":"2021-10-29","cited_by_count":39,"area":null},{"id":"2506.07468","title":"Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models","created":"2025-06-09","cited_by_count":39,"area":"alignment"},{"id":"2205.14691","title":"On the Robustness of Safe Reinforcement Learning under Observational Perturbations","created":"2022-05-29","cited_by_count":38,"area":null},{"id":"2206.06270","title":"Near-Optimal Sample Complexity Bounds for Constrained MDPs","created":"2022-06-13","cited_by_count":37,"area":null},{"id":"2209.08025","title":"Trustworthy Reinforcement Learning Against Intrinsic Vulnerabilities: Robustness, Safety, and Generalizability","created":"2022-09-16","cited_by_count":36,"area":null},{"id":"2106.06239","title":"Safe Reinforcement Learning with Linear Function Approximation","created":"2021-06-11","cited_by_count":35,"area":null},{"id":"2112.00885","title":"DOPE: Doubly Optimistic and Pessimistic Exploration for Safe Reinforcement Learning","created":"2021-12-01","cited_by_count":35,"area":null},{"id":"2305.00316","title":"The Ideal Continual Learner: An Agent That Never Forgets","created":"2023-04-29","cited_by_count":35,"area":null},{"id":"2506.23844","title":"A Survey on Autonomy-Induced Security Risks in Large Model-Based Agents","created":"2025-06-30","cited_by_count":29,"area":"agents"},{"id":"2202.06626","title":"MuZero with Self-competition for Rate Control in VP9 Video Compression","created":"2022-02-14","cited_by_count":28,"area":null},{"id":"2306.11700","title":"Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs","created":"2023-06-20","cited_by_count":28,"area":null},{"id":"2310.03225","title":"Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms","created":"2023-10-05","cited_by_count":28,"area":null},{"id":"2310.05333","title":"DiffCPS: Diffusion Model based Constrained Policy Search for Offline Reinforcement Learning","created":"2023-10-09","cited_by_count":28,"area":"diffusion"},{"id":"2206.02346","title":"Convergence and sample complexity of natural policy gradient primal-dual methods for constrained MDPs","created":"2022-06-06","cited_by_count":27,"area":null},{"id":"2106.12764","title":"Density Constrained Reinforcement Learning","created":"2021-06-24","cited_by_count":25,"area":null},{"id":"2402.15776","title":"Truly No-Regret Learning in Constrained MDPs","created":"2024-02-24","cited_by_count":23,"area":"deeprl"},{"id":"2202.07565","title":"CUP: A Conservative Update Policy Algorithm for Safe Reinforcement Learning","created":"2022-02-15","cited_by_count":20,"area":null},{"id":"2302.01275","title":"ReLOAD: Reinforcement Learning with Optimistic Ascent-Descent for Last-Iterate Convergence in Constrained MDPs","created":"2023-02-02","cited_by_count":20,"area":null},{"id":"2110.10351","title":"Faster Algorithm and Sharper Analysis for Constrained Markov Decision Process","created":"2021-10-20","cited_by_count":19,"area":null},{"id":"2210.07553","title":"Safe Model-Based Reinforcement Learning with an Uncertainty-Aware Reachability Certificate","created":"2022-10-14","cited_by_count":18,"area":null},{"id":"2106.01577","title":"A Provably-Efficient Model-Free Algorithm for Constrained Markov Decision Processes","created":"2021-06-03","cited_by_count":17,"area":null},{"id":"2110.11383","title":"Finite-Time Complexity of Online Primal-Dual Natural Actor-Critic Algorithm for Constrained Markov Decision Processes","created":"2021-10-21","cited_by_count":17,"area":null},{"id":"2212.13769","title":"Lexicographic Multi-Objective Reinforcement Learning","created":"2022-12-28","cited_by_count":17,"area":null},{"id":"2307.03186","title":"TGRL: An Algorithm for Teacher Guided Reinforcement Learning","created":"2023-07-06","cited_by_count":17,"area":"distill"},{"id":"2209.06866","title":"Robust Constrained Reinforcement Learning","created":"2022-09-14","cited_by_count":15,"area":null},{"id":"2212.09010","title":"Risk-Sensitive Reinforcement Learning with Exponential Criteria","created":"2022-12-18","cited_by_count":15,"area":null},{"id":"2306.02426","title":"Resilient Constrained Learning","created":"2023-06-04","cited_by_count":15,"area":null},{"id":"2406.15788","title":"Distributionally Robust Constrained Reinforcement Learning under Strong Duality","created":"2024-06-22","cited_by_count":15,"area":"deeprl"},{"id":"2401.14758","title":"Off-Policy Primal-Dual Safe Reinforcement Learning","created":"2024-01-26","cited_by_count":14,"area":"deeprl"},{"id":"2304.04066","title":"Stable and Safe Reinforcement Learning via a Barrier-Lyapunov Actor-Critic Approach","created":"2023-04-08","cited_by_count":13,"area":null},{"id":"2206.01588","title":"Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games","created":"2022-06-03","cited_by_count":12,"area":null},{"id":"2207.05650","title":"A Single-Loop Gradient Descent and Perturbed Ascent Algorithm for Nonconvex Functional Constrained Optimization","created":"2022-07-12","cited_by_count":12,"area":null},{"id":"2306.17279","title":"Probabilistic Constraint for Safety-Critical Reinforcement Learning","created":"2023-06-29","cited_by_count":11,"area":null},{"id":"2407.00304","title":"A Review of Safe Reinforcement Learning Methods for Modern Power Systems","created":"2024-06-29","cited_by_count":11,"area":"deeprl"},{"id":"2112.09579","title":"Convergence Rates of Two-Time-Scale Gradient Descent-Ascent Dynamics for Solving Nonconvex Min-Max Problems","created":"2021-12-17","cited_by_count":10,"area":null},{"id":"2402.17885","title":"Independent Learning in Constrained Markov Potential Games","created":"2024-02-27","cited_by_count":10,"area":"deeprl"},{"id":"2408.16286","title":"Near-Optimal Policy Identification in Robust Constrained Markov Decision Processes via Epigraph Form","created":"2024-08-29","cited_by_count":10,"area":"deeprl"},{"id":"2409.07569","title":"A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challenges","created":"2024-09-11","cited_by_count":10,"area":"deeprl"},{"id":"2110.06482","title":"Parallel Deep Neural Networks Have Zero Duality Gap","created":"2021-10-13","cited_by_count":9,"area":null},{"id":"2301.13375","title":"Optimal Transport Perturbations for Safe Reinforcement Learning with Robustness Guarantees","created":"2023-01-31","cited_by_count":9,"area":null},{"id":"2204.05176","title":"Towards Painless Policy Optimization for Constrained MDPs","created":"2022-04-11","cited_by_count":8,"area":null},{"id":"2405.01327","title":"Constrained Reinforcement Learning Under Model Mismatch","created":"2024-05-02","cited_by_count":8,"area":"deeprl"},{"id":"2105.12204","title":"Safe Value Functions","created":"2021-05-25","cited_by_count":7,"area":null},{"id":"2111.01616","title":"OnSlicing: Online End-to-End Network Slicing with Reinforcement Learning","created":"2021-11-02","cited_by_count":7,"area":null},{"id":"2306.07001","title":"Cancellation-Free Regret Bounds for Lagrangian Approaches in Constrained Markov Decision Processes","created":"2023-06-12","cited_by_count":7,"area":null},{"id":"2306.07749","title":"Provably Learning Nash Policies in Constrained Markov Potential Games","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2207.01337","title":"Safe Reinforcement Learning via Confidence-Based Filters","created":"2022-07-04","cited_by_count":6,"area":null},{"id":"2208.09106","title":"A Risk-Sensitive Approach to Policy Optimization","created":"2022-08-19","cited_by_count":6,"area":null},{"id":"2311.05511","title":"Anytime-Constrained Reinforcement Learning","created":"2023-11-09","cited_by_count":6,"area":null},{"id":"2401.17780","title":"A Policy Gradient Primal-Dual Algorithm for Constrained MDPs with Uniform PAC Guarantees","created":"2024-01-31","cited_by_count":6,"area":"deeprl"},{"id":"2502.10138","title":"Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation","created":"2025-02-14","cited_by_count":6,"area":"deeprl"},{"id":"2505.19238","title":"Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees","created":"2025-05-25","cited_by_count":6,"area":"deeprl"},{"id":"2209.07437","title":"Mean-Field Approximation of Cooperative Constrained Multi-Agent Reinforcement Learning (CMARL)","created":"2022-09-15","cited_by_count":5,"area":null},{"id":"2405.14183","title":"Deterministic Policies for Constrained Reinforcement Learning in Polynomial Time","created":"2024-05-23","cited_by_count":5,"area":"deeprl"},{"id":"2406.18529","title":"Confident Natural Policy Gradient for Local Planning in $q_\\pi$-realizable Constrained MDPs","created":"2024-06-26","cited_by_count":5,"area":"deeprl"},{"id":"2407.15537","title":"Exterior Penalty Policy Optimization with Penalty Metric Network under Constraints","created":"2024-07-22","cited_by_count":5,"area":"deeprl"},{"id":"2409.09958","title":"An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning","created":"2024-09-16","cited_by_count":5,"area":"deeprl"},{"id":"2410.19933","title":"Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization","created":"2024-10-25","cited_by_count":5,"area":"alignment"},{"id":"2206.01666","title":"Algorithm for Constrained Markov Decision Process with Linear Convergence","created":"2022-06-03","cited_by_count":4,"area":null},{"id":"2210.00301","title":"Learning Globally Smooth Functions on Manifolds","created":"2022-10-01","cited_by_count":4,"area":null},{"id":"2304.08845","title":"Feasible Policy Iteration for Safe Reinforcement Learning","created":"2023-04-18","cited_by_count":4,"area":null},{"id":"2312.17503","title":"HiBid: A Cross-Channel Constrained Bidding System with Budget Allocation by Hierarchical Offline Deep Reinforcement Learning","created":"2023-12-29","cited_by_count":4,"area":"offlinerl"},{"id":"2402.00355","title":"Adaptive Primal-Dual Method for Safe Reinforcement Learning","created":"2024-02-01","cited_by_count":4,"area":"deeprl"},{"id":"2403.04007","title":"Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems","created":"2024-03-06","cited_by_count":4,"area":"deeprl"},{"id":"2410.02236","title":"C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front","created":"2024-10-03","cited_by_count":4,"area":"deeprl"},{"id":"2410.03955","title":"A Retention-Centric Framework for Continual Learning with Guaranteed Model Developmental Safety","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2508.17448","title":"Rectified Robust Policy Optimization for Model-Uncertain Constrained Reinforcement Learning without Strong Duality","created":"2025-08-24","cited_by_count":4,"area":"deeprl"},{"id":"2509.16586","title":"Near-Optimal Sample Complexity Bounds for Constrained Average-Reward MDPs","created":"2025-09-20","cited_by_count":4,"area":null},{"id":"2108.02701","title":"Lyapunov Robust Constrained-MDPs: Soft-Constrained Robustly Stable Policy Optimization under Model Uncertainty","created":"2021-08-05","cited_by_count":3,"area":null},{"id":"2212.01505","title":"Constrained Reinforcement Learning via Dissipative Saddle Flow Dynamics","created":"2022-12-03","cited_by_count":3,"area":null},{"id":"2309.02669","title":"Marketing Budget Allocation with Offline Constrained Deep Reinforcement Learning","created":"2023-09-06","cited_by_count":3,"area":null},{"id":"2401.09640","title":"Blackout Mitigation via Physics-guided RL","created":"2024-01-17","cited_by_count":3,"area":null},{"id":"2406.01782","title":"Multi-agent assignment via state augmented reinforcement learning","created":"2024-06-03","cited_by_count":3,"area":null},{"id":"2407.03995","title":"ROER: Regularized Optimal Experience Replay","created":"2024-07-04","cited_by_count":3,"area":"deeprl"},{"id":"2410.06474","title":"Flipping-based Policy for Chance-Constrained Markov Decision Processes","created":"2024-10-09","cited_by_count":3,"area":"deeprl"},{"id":"2605.05750","title":"RVPO: Risk-Sensitive Alignment via Variance Regularization","created":"2026-05-07","cited_by_count":3,"area":"alignment"},{"id":"2102.12585","title":"Towards Safe Continuing Task Reinforcement Learning","created":"2021-02-24","cited_by_count":2,"area":null},{"id":"2211.05361","title":"Safety-Constrained Policy Transfer with Successor Features","created":"2022-11-10","cited_by_count":2,"area":null},{"id":"2303.04118","title":"A Multiplicative Value Function for Safe and Efficient Reinforcement Learning","created":"2023-03-07","cited_by_count":2,"area":null},{"id":"2405.03236","title":"Federated Reinforcement Learning with Constraint Heterogeneity","created":"2024-05-06","cited_by_count":2,"area":"deeprl"},{"id":"2405.05748","title":"Learning to Slice Wi-Fi Networks: A State-Augmented Primal-Dual Approach","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2405.11669","title":"Do No Harm: A Counterfactual Approach to Safe Reinforcement Learning","created":"2024-05-19","cited_by_count":2,"area":"deeprl"},{"id":"2407.10775","title":"Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning","created":"2024-07-15","cited_by_count":2,"area":"deeprl"},{"id":"2503.06751","title":"Primal-Dual Sample Complexity Bounds for Constrained Markov Decision Processes with Multiple Constraints","created":"2025-03-09","cited_by_count":2,"area":"deeprl"},{"id":"2504.16417","title":"Anytime Safe Reinforcement Learning","created":"2025-04-23","cited_by_count":2,"area":"deeprl"},{"id":"2510.20199","title":"Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents","created":"2025-10-23","cited_by_count":2,"area":"deeprl"},{"id":"2604.19024","title":"Policy Gradient Primal-Dual Method for Safe Reinforcement Learning from Human Feedback","created":"2026-04-21","cited_by_count":2,"area":"alignment"},{"id":"2605.11586","title":"Learning Weakly Communicating Average-Reward CMDPs: Strong Duality and Improved Regret","created":"2026-05-12","cited_by_count":2,"area":"deeprl"},{"id":"2111.05670","title":"DeCOM: Decomposed Policy for Constrained Cooperative Multi-Agent Reinforcement Learning","created":"2021-11-10","cited_by_count":1,"area":null},{"id":"2312.17194","title":"Resilient Constrained Reinforcement Learning","created":"2023-12-28","cited_by_count":1,"area":null},{"id":"2401.07051","title":"COIN: Chance-Constrained Imitation Learning for Uncertainty-aware Adaptive Resource Oversubscription Policy","created":"2024-01-13","cited_by_count":1,"area":"offlinerl"},{"id":"2404.07315","title":"Structured Reinforcement Learning for Media Streaming at the Wireless Edge","created":"2024-04-10","cited_by_count":1,"area":"deeprl"},{"id":"2404.16468","title":"A Dual Perspective of Reinforcement Learning for Imposing Policy Constraints","created":"2024-04-25","cited_by_count":1,"area":"deeprl"},{"id":"2406.03734","title":"Policy Gradient Methods for the Cost-Constrained LQR: Strong Duality and Global Convergence","created":"2024-06-06","cited_by_count":1,"area":"deeprl"}],"next_cursor":"100"}